Files

599 lines
20 KiB
Rust

use agen::EngineResult;
use agen::llm_client::types::{Item, RequestConfig};
use session_store::{
FsStore, LogEntry, LoggedHistoryEntry, LoggedItem, LoggedSessionHistoryEntryId,
LoggedSessionHistoryMetadata, LoggedSessionHistoryOrigin, Store, TraceEntry, collect_state,
new_segment_id, new_session_id,
};
use std::io::Write;
fn annotated(item: Item) -> LoggedHistoryEntry {
LoggedHistoryEntry {
item: LoggedItem::from(item),
metadata: LoggedSessionHistoryMetadata {
input_metadata: None,
entry_id: LoggedSessionHistoryEntryId::new(),
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
derivation: None,
},
}
}
fn nil_session_start(ts: u64, session_id: uuid::Uuid) -> LogEntry {
LogEntry::AnnotatedSegmentStart {
ts,
session_id,
system_prompt: None,
config: RequestConfig::default(),
history: vec![],
forked_from: None,
compacted_from: None,
}
}
#[test]
fn round_trip_write_and_read() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let entries = vec![
LogEntry::AnnotatedSegmentStart {
ts: 1000,
session_id: sid,
system_prompt: Some("You are helpful.".into()),
config: RequestConfig::default().with_max_tokens(1024),
history: vec![],
forked_from: None,
compacted_from: None,
},
LogEntry::AnnotatedUserInput {
ts: 2000,
extensions: vec![],
segments: vec![protocol::Segment::text("Hello")],
history: vec![annotated(Item::user_message("Hello"))],
},
LogEntry::AnnotatedAssistantItem {
ts: 3000,
entry: annotated(Item::assistant_message("Hi there!")),
},
LogEntry::TurnEnd {
ts: 3100,
turn_count: 1,
},
LogEntry::RunCompleted {
entry_id: None,
ts: 3200,
interrupted: false,
result: EngineResult::Finished,
active_run_turn_count: None,
},
];
for entry in &entries {
store.append(sid, segid, entry).unwrap();
}
let read_back = store.read_all(sid, segid).unwrap();
assert_eq!(read_back.len(), entries.len());
let state = collect_state(&read_back);
assert_eq!(state.session_id, Some(sid));
assert_eq!(state.system_prompt.as_deref(), Some("You are helpful."));
assert_eq!(state.config.max_tokens, Some(1024));
assert_eq!(state.history.len(), 2);
assert_eq!(state.turn_count, 1);
assert!(!state.last_run_interrupted);
assert_eq!(state.entries_count, entries.len());
}
#[test]
fn create_segment_writes_all_entries() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let entries = [LogEntry::AnnotatedSegmentStart {
ts: 1000,
session_id: sid,
system_prompt: None,
config: RequestConfig::default(),
history: vec![
annotated(Item::user_message("seed")),
annotated(Item::assistant_message("ok")),
],
forked_from: None,
compacted_from: None,
}];
store.create_segment(sid, segid, &entries).unwrap();
let read_back = store.read_all(sid, segid).unwrap();
assert_eq!(read_back.len(), 1);
let state = collect_state(&read_back);
assert_eq!(state.history.len(), 2);
assert_eq!(state.session_id, Some(sid));
}
#[test]
fn create_segment_replacement_keeps_open_old_log_and_commits_complete_new_log() {
use std::io::Read;
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let old = vec![
nil_session_start(1, sid),
LogEntry::TurnEnd {
ts: 2,
turn_count: 1,
},
];
store.create_segment(sid, segid, &old).unwrap();
let path = dir
.path()
.join(sid.to_string())
.join(format!("{segid}.jsonl"));
let old_bytes = std::fs::read(&path).unwrap();
let mut old_reader = std::fs::File::open(&path).unwrap();
let new = vec![
nil_session_start(1, sid),
LogEntry::Extension {
ts: 3,
domain: "recovery-checkpoint".into(),
payload: serde_json::json!({"receipt": "retained"}),
},
];
store.create_segment(sid, segid, &new).unwrap();
let mut retained_inode = Vec::new();
old_reader.read_to_end(&mut retained_inode).unwrap();
// An in-place fs::write would truncate the inode held by this reader.
assert_eq!(retained_inode, old_bytes);
let reopened = FsStore::new(dir.path()).unwrap();
assert_eq!(
serde_json::to_value(reopened.read_all(sid, segid).unwrap()).unwrap(),
serde_json::to_value(&new).unwrap()
);
assert_eq!(reopened.read_entry_count(sid, segid).unwrap(), new.len());
assert_eq!(
std::fs::read_dir(path.parent().unwrap()).unwrap().count(),
2,
"successful replacement leaves only the segment and Session schema marker"
);
assert!(path.parent().unwrap().join("session-schema.json").is_file());
}
#[test]
fn create_segment_atomic_replacement_readers_only_observe_complete_old_or_new() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let old = vec![
nil_session_start(1, sid),
LogEntry::Extension {
ts: 2,
domain: "old-evidence".into(),
payload: serde_json::json!({"result": "old"}),
},
];
let new = vec![
nil_session_start(1, sid),
LogEntry::Extension {
ts: 3,
domain: "new-checkpoint".into(),
payload: serde_json::json!({"result": "new"}),
},
];
store.create_segment(sid, segid, &old).unwrap();
let old_json = serde_json::to_value(&old).unwrap();
let new_json = serde_json::to_value(&new).unwrap();
let barrier = std::sync::Arc::new(std::sync::Barrier::new(2));
let reader_store = store.clone();
let reader_barrier = barrier.clone();
let reader = std::thread::spawn(move || {
reader_barrier.wait();
for _ in 0..1000 {
let observed =
serde_json::to_value(reader_store.read_all(sid, segid).unwrap()).unwrap();
assert!(
observed == old_json || observed == new_json,
"replacement must never expose a partial log: {observed}"
);
}
});
barrier.wait();
for _ in 0..50 {
store.create_segment(sid, segid, &new).unwrap();
store.create_segment(sid, segid, &old).unwrap();
}
reader.join().unwrap();
}
#[test]
fn list_sessions_and_segments() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid_a = new_session_id();
std::thread::sleep(std::time::Duration::from_millis(2));
let sid_b = new_session_id();
let seg_a1 = new_segment_id();
let seg_a2 = new_segment_id();
let seg_b1 = new_segment_id();
store
.append(sid_a, seg_a1, &nil_session_start(1, sid_a))
.unwrap();
store
.append(sid_a, seg_a2, &nil_session_start(2, sid_a))
.unwrap();
store
.append(sid_b, seg_b1, &nil_session_start(3, sid_b))
.unwrap();
let sessions = store.list_sessions().unwrap();
assert_eq!(sessions, vec![sid_b, sid_a]); // newest first
let segs_a = store.list_segments(sid_a).unwrap();
assert!(segs_a.contains(&seg_a1) && segs_a.contains(&seg_a2));
assert_eq!(segs_a.len(), 2);
let segs_b = store.list_segments(sid_b).unwrap();
assert_eq!(segs_b, vec![seg_b1]);
}
#[test]
fn exists_returns_correct_state() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
assert!(!store.exists(sid, segid).unwrap());
store
.append(sid, segid, &nil_session_start(1000, sid))
.unwrap();
assert!(store.exists(sid, segid).unwrap());
}
#[test]
fn not_found_error_for_missing_segment() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let result = store.read_all(sid, segid);
assert!(result.is_err());
}
#[test]
fn trace_entries_in_separate_file() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
store
.append(sid, segid, &nil_session_start(1000, sid))
.unwrap();
let trace = TraceEntry {
ts: 1500,
turn: 0,
llm_call: Some(0),
payload: session_store::TracePayload::StreamEvent {
event: agen::llm_client::event::Event::Ping(agen::llm_client::event::PingEvent {
timestamp: None,
}),
},
};
store.append_trace(sid, segid, &trace).unwrap();
// Log should have 1 entry, unaffected by trace
let log = store.read_all(sid, segid).unwrap();
assert_eq!(log.len(), 1);
// Trace file should exist separately
let trace_path = dir
.path()
.join(sid.to_string())
.join(format!("{segid}.trace.jsonl"));
assert!(trace_path.exists());
}
#[test]
fn read_entry_count_matches_append_tally() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let entries = [
LogEntry::AnnotatedSegmentStart {
ts: 1000,
session_id: sid,
system_prompt: None,
config: RequestConfig::default(),
history: vec![],
forked_from: None,
compacted_from: None,
},
LogEntry::AnnotatedUserInput {
ts: 2000,
extensions: vec![],
segments: vec![protocol::Segment::text("Hello")],
history: vec![annotated(Item::user_message("Hello"))],
},
];
for entry in &entries {
store.append(sid, segid, entry).unwrap();
}
assert_eq!(store.read_entry_count(sid, segid).unwrap(), entries.len());
}
#[test]
fn unterminated_utf8_tail_is_ignored_and_replaced_on_append() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let path = dir
.path()
.join(sid.to_string())
.join(format!("{segid}.jsonl"));
store
.append(sid, segid, &nil_session_start(1, sid))
.unwrap();
std::fs::OpenOptions::new()
.append(true)
.open(&path)
.unwrap()
// First byte of a three-byte UTF-8 code point, matching an ENOSPC
// partial write observed in a real session log.
.write_all(&[0xe3])
.unwrap();
assert_eq!(store.read_all(sid, segid).unwrap().len(), 1);
assert_eq!(store.read_entry_count(sid, segid).unwrap(), 1);
let next = LogEntry::AnnotatedUserInput {
ts: 2,
extensions: vec![],
segments: vec![protocol::Segment::text("recovered")],
history: vec![annotated(Item::user_message("recovered"))],
};
store.append(sid, segid, &next).unwrap();
let bytes = std::fs::read(&path).unwrap();
assert!(std::str::from_utf8(&bytes).is_ok());
assert_eq!(store.read_all(sid, segid).unwrap().len(), 2);
assert_eq!(store.read_entry_count(sid, segid).unwrap(), 2);
}
#[test]
fn newline_terminated_invalid_utf8_is_reported_as_corruption() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
let path = dir
.path()
.join(sid.to_string())
.join(format!("{segid}.jsonl"));
store
.append(sid, segid, &nil_session_start(1, sid))
.unwrap();
std::fs::OpenOptions::new()
.append(true)
.open(path)
.unwrap()
.write_all(&[0xe3, b'\n'])
.unwrap();
assert!(matches!(
store.read_all(sid, segid),
Err(session_store::StoreError::Corrupt { line: 2, .. })
));
}
#[test]
fn lookup_session_of_finds_owning_session() {
let dir = tempfile::tempdir().unwrap();
let store = FsStore::new(dir.path()).unwrap();
let sid = new_session_id();
let segid = new_segment_id();
assert_eq!(store.lookup_session_of(segid).unwrap(), None);
store
.append(sid, segid, &nil_session_start(1, sid))
.unwrap();
assert_eq!(store.lookup_session_of(segid).unwrap(), Some(sid));
}
// Storage/projection component test: both production layouts, temporary originals,
// no Feature, model, runtime or Host authority is substituted into this boundary.
#[test]
fn generic_system_append_and_fork_preserve_metadata_without_public_payload_leak() {
use session_store::{
FeatureInputPayload, HistoryInputMetadata, HistoryInputUsePolicy, InputCompactionUse,
InputEvidenceUse, InputObservationUse, LoggedHistoryDerivation, LoggedSystemHistoryEntry,
PublicSystemItem, PublicSystemPresentation, SystemInputEnvelope, WorkerSessionStore,
};
for worker_layout in [false, true] {
let dir = tempfile::tempdir().unwrap();
let sid = new_session_id();
let segment = new_segment_id();
let fork = new_segment_id();
let store: Box<dyn Store> = if worker_layout {
Box::new(WorkerSessionStore::new(dir.path()).unwrap())
} else {
Box::new(FsStore::new(dir.path()).unwrap())
};
store
.create_segment(sid, segment, &[nil_session_start(1, sid)])
.unwrap();
let entry = LoggedSystemHistoryEntry::from_input(
LoggedSessionHistoryOrigin::Provided {
producer: "new-feature".into(),
},
Some(LoggedHistoryDerivation {
sources: vec![LoggedSessionHistoryEntryId("source-entry".into())],
}),
SystemInputEnvelope::new(
"private model body",
HistoryInputMetadata::new(
HistoryInputUsePolicy {
recording_material: InputEvidenceUse::Exclude,
memory_evidence: InputEvidenceUse::Exclude,
observation: InputObservationUse::Hidden,
compaction: InputCompactionUse::ReferenceInput,
},
Some(
FeatureInputPayload::encode(
"new-feature:context",
101,
&serde_json::json!({"private": "secret-detail"}),
)
.unwrap(),
),
Some(PublicSystemItem {
kind: "context".into(),
body: "explicit public body".into(),
presentation: PublicSystemPresentation::Context,
}),
)
.unwrap(),
)
.unwrap(),
);
store
.append(
sid,
segment,
&LogEntry::AnnotatedSystemItem {
ts: 2,
entry: entry.clone(),
extensions: vec![],
},
)
.unwrap();
let saved = store.read_all(sid, segment).unwrap();
let LogEntry::AnnotatedSystemItem {
entry: restored, ..
} = &saved[1]
else {
panic!("missing system input")
};
assert_eq!(restored.to_history_entry(), entry.to_history_entry());
assert_eq!(
collect_state(&saved).history[0].as_text(),
Some("private model body")
);
let mut fork_seed = nil_session_start(3, sid);
if let LogEntry::AnnotatedSegmentStart {
history,
forked_from,
..
} = &mut fork_seed
{
history.push(restored.to_history_entry());
*forked_from = Some(session_store::SegmentOrigin {
segment_id: segment,
at_turn_index: 0,
});
}
store.create_segment(sid, fork, &[fork_seed]).unwrap();
let fork_saved = store.read_all(sid, fork).unwrap();
let LogEntry::AnnotatedSegmentStart { history, .. } = &fork_saved[0] else {
unreachable!()
};
assert_eq!(history, &[entry.to_history_entry()]);
let original = session_store::public_snapshot::project_session_snapshot(sid, &saved);
let inherited = session_store::public_snapshot::project_session_snapshot(sid, &fork_saved);
let public = serde_json::to_string(&original.entries).unwrap();
assert!(public.contains("explicit public body"));
for private in ["private model body", "secret-detail", "new-feature:context"] {
assert!(!public.contains(private), "private field leaked: {private}");
}
assert_eq!(original.entries.len(), 1);
assert_eq!(inherited.entries.len(), 1);
assert_eq!(original.entries[0].entry_id, inherited.entries[0].entry_id);
assert_eq!(
original.entries[0].derived_from,
inherited.entries[0].derived_from
);
assert_eq!(
original.entries[0].provenance,
inherited.entries[0].provenance
);
assert_eq!(
serde_json::to_value(&original.entries[0].data).unwrap(),
serde_json::to_value(&inherited.entries[0].data).unwrap()
);
}
}
#[test]
fn invalid_generic_system_input_rejects_append_create_and_external_json_without_changing_originals()
{
use session_store::{StoreError, SystemItem, WorkerSessionStore};
for worker_layout in [false, true] {
let dir = tempfile::tempdir().unwrap();
let sid = new_session_id();
let segment = new_segment_id();
let store: Box<dyn Store> = if worker_layout {
Box::new(WorkerSessionStore::new(dir.path()).unwrap())
} else {
Box::new(FsStore::new(dir.path()).unwrap())
};
let seed = nil_session_start(1, sid);
store
.create_segment(sid, segment, std::slice::from_ref(&seed))
.unwrap();
let path = if worker_layout {
dir.path().join("segments").join(format!("{segment}.jsonl"))
} else {
dir.path()
.join(sid.to_string())
.join(format!("{segment}.jsonl"))
};
let before = std::fs::read(&path).unwrap();
let invalid = LogEntry::AnnotatedSystemItem {
ts: 2,
extensions: vec![],
entry: session_store::LoggedSystemHistoryEntry {
item: SystemItem::Input {
body: "no policy".into(),
},
metadata: LoggedSessionHistoryMetadata::legacy_unknown(),
},
};
assert!(matches!(
store.append(sid, segment, &invalid),
Err(StoreError::InvalidInputMetadata(_))
));
assert!(matches!(
store.create_segment(sid, segment, &[seed, invalid.clone()]),
Err(StoreError::InvalidInputMetadata(_))
));
assert!(
serde_json::from_value::<LogEntry>(serde_json::to_value(invalid).unwrap()).is_err()
);
assert_eq!(std::fs::read(path).unwrap(), before);
assert_eq!(store.read_all(sid, segment).unwrap().len(), 1);
}
}